适于少样本缺陷检测的两阶段缺陷增强网络

doi:10.3778/j.issn.1002-8331.2111-0470

摘要/Abstract

摘要： 缺陷检测模型一般需要大量样本来学习缺陷的特征，但实际场景中一些重要缺陷的样本难以收集，如何用少量样本来学习罕见缺陷的特征成为一个具有挑战性的问题。为了促进少样本缺陷检测的研究，构建了一个新的工业表面缺陷数据集，包括缺陷样本和无缺陷样本。同时提出了一个两阶段缺陷增强网络以提升少样本场景下的缺陷检测性能，它利用了无缺陷样本，并将整个训练过程分为两个阶段。第一阶段的训练需要大量缺陷样本，而第二阶段的训练只需要少量缺陷样本和无缺陷样本。此外，还提出了一个缺陷突显模块，可以更好地利用无缺陷样本来增强缺陷区域的特征。在新数据集上的实验表明，该缺陷检测模型的性能优于其他的少样本目标检测模型，在工业表面缺陷检测中具有更好的应用前景。

关键词: 缺陷检测, 少样本学习, 无缺陷样本, 两阶段缺陷增强网络, 缺陷突显模块

Abstract: Defect detection models generally require many training samples to learn the characteristics of defects, however, some important defects are often difficult to collect in the actual scene. How to learn the characteristics of these rare defects with few training samples becomes a challenging issue. To facilitate the study of few-shot defect detection, a new industrial surface defects dataset is constructed, including defect samples and defect-free samples. Meanwhile, a two-phase defect enhancement network is proposed to improve the performance of defect detection when only few samples are provided, which utilizes defect-free samples, and the whole training process is divided into two phases. The first phase needs many defect samples, while the second phase only needs few defect samples and defect-free samples. In addition, a defect prominence module is proposed, which makes better use of defect-free samples to enhance the characteristics of defective areas. Experiments on the new dataset show that the proposed defect detection model outperforms other few-shot object detection models and has a better application prospect in industrial surface defect detection.

Key words: defect detection, few-shot learning, defect-free samples, two-phase defect enhancement network, defect prominence module

陈朝, 刘志, 李恭杨, 彭铁根. 适于少样本缺陷检测的两阶段缺陷增强网络[J]. 计算机工程与应用, 2022, 58(20): 108-116.

CHEN Zhao, LIU Zhi, LI Gongyang, PENG Tiegen. Two-Phase Defect Enhancement Network for Few-Shot Defect Detection[J]. Computer Engineering and Applications, 2022, 58(20): 108-116.

参考文献

[1] 张艺超，侯艳杰，陈君华，等.少样本学习[J].云南民族大学学报（自然科学版），2020，29（6）：582-591.
ZHANG Y C，HOU Y J，CHEN J H，et al.Few-shot learning[J].Journal of Yunnan Nationalities University（Natural Sciences Edition），2020，29（6）：582-591.
[2] KANG B，LIU Z，WANG X，et al.Few-shot object detection via feature reweighting[C]//Proc IEEE Int Conf Comput Vis，2019：8419-8428.
[3] YAN X，CHEN Z，XU A，et al.Meta R-CNN：towards general solver for instance-level low-shot learning[C]//Proc IEEE Int Conf Comput Vis，2019：9576-9585.
[4] YANG X，MARLET R.Few-shot object detection and viewpoint estimation for objects in the wild[C]//European Conference on Computer Vision.Cham：Springer，2020：192-210.
[5] BORSELLI A，COLLA V，VANNUCCI M，et al.A fuzzy inference system applied to defect detection in flat steel production[C]//IEEE International Conference on Fuzzy Systems，2010.
[6] 李军华，权小霞，汪宇玲.多特征融合的瓷砖表面缺陷检测算法研究[J].计算机工程与应用，2020，56（15）：191-198.
LI J H，QUAN X X，WANG Y L.Research on defect detection algorithm of ceramic tile surface with multi-feature fusion[J].Computer Engineering and Applications，2020，56（15）：191-198.
[7] TOLBA A S.Fast defect detection in homogeneous flat surface products[J].Expert Systems with Applications，2011，38（10）：12339-12347.
[8] KIM J，UM S，MIN D.Fast 2D complex gabor filter with kernel decomposition[J].IEEE Transactions on Image Processing，2018，27：1713-1722.
[9] 黄梦涛，连一鑫.基于改进Canny算子的锂电池极片表面缺陷检测[J].仪器仪表学报，2021，42（10）：199-209.
HUANG M T，LIAN Y X.Lithium battery electrode plate surface defect detection based on improved Canny operator[J].Chinese Journal of Scientific Instrument，2021，42（10）：199-209.
[10] YI L，LI G，JIANG M.An end-to-end steel strip surface defects recognition system based on convolutional neural networks[J].Steel Research International，2017，88：176-187.
[11] REN Q，GENG J，LI J.Slighter Faster R-CNN for real-time detection of steel strip surface defects[C]//2018 Chinese Automation Congress（CAC），2018：2173-2178.
[12] 徐镪，朱洪锦，范洪辉，等.改进的YOLOv3网络在钢板表面缺陷检测研究[J].计算机工程与应用，2020，56（16）：265-272.
XU Q，ZHU H J，FAN H H，et al.Study on detection of steel plate surface defects by improved YOLOv3 network[J].Computer Engineering and Applications，2020，56（16）：265-272.
[13] REDMON J，FARHADI A.YOLOv3：an incremental improvement[C]//2018 IEEE Conference on Computer Vision and Pattern Recognition，2018.
[14] 李钧正，殷子玉，乐心怡.基于小样本学习的钢板表面缺陷检测技术[J].航空科学技术，2021，32（6）：65-70.
LI J Z，YIN Z Y，YUE X Y.Surface defect detection for steel plate with small dataset[J].Aeronautical Science & Technology，2021，32（6）：65-70.
[15] WANG H，LI Z，WANG H.Few-shot steel surface defect detection[J].IEEE Transactions on Instrumentation and Measurement，2021，71：5003912.
[16] 张艺桥.基于深度学习的少样本缺陷检测的研究与实现[D].大连：大连理工大学，2021.
ZHANG Y Q.Research and implementation of defect detection with few samples based on deep learning[D].Dalian：Dalian University of Technology，2021.
[17] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2017，39（6）：1137-1149.
[18] SONG K，YAN Y.A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects[J].Applied Surface Science，2013，285（21）：858-864.
[19] HUANG Y，QIU C，GUO Y，et al.Surface defect saliency of magnetic tile[J].Visual Computer，2018：612-617.
[20] 任喜伟，何立风，宋安玲，等.基于连通域标记的原油乳状液粒径检测算法[J].计算机应用与软件，2021，38（7）：196-201.
REN X W，HE L F，SONG A L，et al.A droplet size detection algorithm for crude oil emulsion based on connected-component-labeling[J].Computer Applications and Software，2021，38（7）：196-201.
[21] BERGMANN P，FAUSER M，SATTLEGGER D，et al.MVTec AD—a comprehensive real-world dataset for unsupervised anomaly detection[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2020.
[22] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[J].2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2016：770-778.